From b56fdf188ed95d7db6457caec8f3008c4f0e97f4 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Wed, 18 Mar 2026 17:57:27 +0530 Subject: [PATCH] Fix greptile review --- .../docs/tutorials/vertex_ai_pay_go.md | 4 +-- .../static/img/vertex_cost_tracking_flow.svg | 27 ++++++++++--------- 2 files changed, 16 insertions(+), 15 deletions(-) diff --git a/docs/my-website/docs/tutorials/vertex_ai_pay_go.md b/docs/my-website/docs/tutorials/vertex_ai_pay_go.md index 625aff35e1b..b40a8b2157f 100644 --- a/docs/my-website/docs/tutorials/vertex_ai_pay_go.md +++ b/docs/my-website/docs/tutorials/vertex_ai_pay_go.md @@ -124,7 +124,7 @@ MODEL_ID="gemini-2.0-flash-001" PROJECT_ID="YOUR_PROJECT_ID" curl -X POST \ - "${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:generateContent" \ + "${LITELLM_PROXY_BASE_URL}/vertex_ai/v1/projects/${PROJECT_ID}/locations/global/publishers/google/models/${MODEL_ID}:generateContent" \ -H "Authorization: Bearer sk-your-litellm-key" \ -H "Content-Type: application/json" \ -H "x-pass-X-Vertex-AI-LLM-Request-Type: shared" \ @@ -143,7 +143,7 @@ A: The service account or Application Default Credentials (ADC) user does not ha **Q: What should I do if I get a `429 Quota exceeded` error?** A: This means you've hit the per-region QPM (queries per minute) or TPM (tokens per minute) quota. You can: - Request a quota increase from the [GCP Quotas console](https://console.cloud.google.com/iam-admin/quotas) -- Add more regions to your LiteLLM configuration for load balancing (see the region balancing guide above) +- Add more regions to your LiteLLM configuration for load balancing - Upgrade to [Provisioned Throughput](https://cloud.google.com/vertex-ai/generative-ai/docs/provisioned-throughput) for guaranteed capacity **Q: How do I fix the `VERTEXAI_PROJECT not set` error?** diff --git a/docs/my-website/static/img/vertex_cost_tracking_flow.svg b/docs/my-website/static/img/vertex_cost_tracking_flow.svg index d808dd2e363..d607d072dd5 100644 --- a/docs/my-website/static/img/vertex_cost_tracking_flow.svg +++ b/docs/my-website/static/img/vertex_cost_tracking_flow.svg @@ -6,7 +6,7 @@ - + HTTP request X-Vertex-AI-LLM-Shared-Request-Type: priority @@ -17,7 +17,7 @@ Vertex AI - + Vertex response usageMetadata.trafficType = ON_DEMAND_PRIORITY @@ -27,7 +27,7 @@ - + LiteLLM stores it _hidden_params.provider_specific_fields.traffic_type @@ -37,26 +37,27 @@ - + completion_cost() - Maps traffic_type ’ service_tier = "priority" + Maps traffic_type → service_tier = "priority" - + Pricing lookup input/output_cost_per_token_priority - - ` - a - b - c - d - + + â‘  + â‘¡ + â‘¢ + â‘£ + ⑤ + + \ No newline at end of file